English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Graph convolution networks (GCN) have been widely used in skeleton-basedaction recognition. We note that existing GCN-based approaches primarily relyon prescribed graphical structures (ie., a manually defined topology ofskeleton joints), which limits their flexibility to capture complicatedcorrelations between joints. To move beyond this limitation, we propose a newframework for skeleton-based action recognition, namely Dynamic GroupSpatio-Temporal GCN (DG-STGCN). It consists of two modules, DG-GCN and DG-TCN,respectively, for spatial and temporal modeling. In particular, DG-GCN useslearned affinity matrices to capture dynamic graphical structures instead ofrelying on a prescribed one, while DG-TCN performs group-wise temporalconvolutions with varying receptive fields and incorporates a dynamicjoint-skeleton fusion module for adaptive multi-level temporal modeling. On awide range of benchmarks, including NTURGB+D, Kinetics-Skeleton, BABEL, andToyota SmartHome, DG-STGCN consistently outperforms state-of-the-art methods,often by a notable margin.

DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition